Synthetic aperture radar image change detection method and device

The invention provides a synthetic aperture radar image change detection method and device, and the method comprises the steps: obtaining a first feature vector through a saliency detection method based on a to-be-detected synthetic aperture radar image; obtaining a second feature vector through a neighborhood ratio method based on the to-be-detected synthetic aperture radar image; and processing the first feature vector and the second feature vector by using a K-means clustering algorithm, and detecting a changing region and an unchanged region in the to-be-detected synthetic aperture radar image. The method is an innovative SAR image change area detection method based on combination of significance detection and neighborhood information. The method is based on a clustering model, and feature vectors of the method are generated from significance detection and a neighborhood information model. According to the method, full-automatic work can be achieved, the defects in a traditional method are overcome, chang